A fine-tuned DeBERTa-v3-base model designed specifically to classify text for prompt injection and related LLM security threats. It can be used as a safeguard layer in LLM-powered applications. Available in Transformers and ONNX formats with training datasets and evaluation results provided.
In the Other AI space, Deberta V3 Base Prompt Injection takes a focused approach. It focuses on identifying malicious prompt injection attempts in LLM inputs to improve application security. Deberta V3 Base Prompt Injection is an open-source project aimed at developers. The project is open source (MIT). It runs on the web and API.
Protect AI builds and maintains Deberta V3 Base Prompt Injection, and the product first shipped in 2023. The GitHub repository has been archived. Among its 3 catalogued features are Prompt Injection Detection, Text Classification, and security.
Latest indexed changes and source events
protectai/deberta-v3-base-prompt-injection-v2 verified by the PulseGate indexer
⚠ Archived
